OpenLB
Open Library of Bioscience
Advanced Search
European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society
08, 2022;31 (8): 2031-2045.

Spinopelvic measurements of sagittal balance with deep learning: systematic review and critical evaluation.

Tomaž Vrtovec, Bulat Ibragimov
Author Information
  1. Tomaž Vrtovec: Laboratory of Imaging Technologies, Faculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, 1000, Ljubljana, Slovenia. tomaz.vrtovec@fe.uni-lj.si. ORCID
  2. Bulat Ibragimov: Laboratory of Imaging Technologies, Faculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, 1000, Ljubljana, Slovenia. ORCID
PMID: 35278146 DOI: 10.1007/s00586-022-07155-5

Abstract

PURPOSE: To summarize and critically evaluate the existing studies for spinopelvic measurements of sagittal balance that are based on deep learning (DL).
METHODS: Three databases (PubMed, WoS and Scopus) were queried for records using keywords related to DL and measurement of sagittal balance. After screening the resulting 529 records that were augmented with specific web search, 34 studies published between 2017 and 2022 were included in the final review, and evaluated from the perspective of the observed sagittal spinopelvic parameters, properties of spine image datasets, applied DL methodology and resulting measurement performance.
RESULTS: Studies reported DL measurement of up to 18 different spinopelvic parameters, but the actual number depended on the image field of view. Image datasets were composed of lateral lumbar spine and whole spine X-rays, biplanar whole spine X-rays and lumbar spine magnetic resonance cross sections, and were increasing in size or enriched by augmentation techniques. Spinopelvic parameter measurement was approached either by landmark detection or structure segmentation, and U-Net was the most frequently applied DL architecture. The latest DL methods achieved excellent performance in terms of mean absolute error against reference manual measurements (~ 2° or ~ 1 mm).
CONCLUSION: Although the application of relatively complex DL architectures resulted in an improved measurement accuracy of sagittal spinopelvic parameters, future methods should focus on multi-institution and multi-observer analyses as well as uncertainty estimation and error handling implementations for integration into the clinical workflow. Further advances will enhance the predictive analytics of DL methods for spinopelvic parameter measurement.
LEVEL OF EVIDENCE I: Diagnostic: individual cross-sectional studies with the consistently applied reference standard and blinding.

Keywords

Artificial intelligence Deep learning Predictive analytics Sagittal balance Spinopelvic measurements Systematic review

References

  1. Vrtovec T, Pernuš F, Likar B (2019) A review of methods for quantitative evaluation of spinal curvature. Eur Spine J 18:593–607. https://doi.org/10.1007/s00586-009-0913-0 [DOI: 10.1007/s00586-009-0913-0]
  2. Vrtovec T, Pernuš F, Likar B (2019) A review of methods for quantitative evaluation of axial vertebral rotation. Eur Spine J 18:1079–1090. https://doi.org/10.1007/s00586-009-0914-z [DOI: 10.1007/s00586-009-0914-z]
  3. Vrtovec T, Janssen MMA, Likar B et al (2012) A review of methods for evaluating the quantitative parameters of sagittal pelvic alignment. Spine J 12:433–446. https://doi.org/10.1016/j.spinee.2012.02.013 [DOI: 10.1016/j.spinee.2012.02.013]
  4. Le Huec J-C, Thompson W, Mohsinaly Y et al (2019) Sagittal balance of the spine. Eur Spine J 28:1889–1905. https://doi.org/10.1007/s00586-019-06083-1 [DOI: 10.1007/s00586-019-06083-1]
  5. Maillot C, Ferrero E, Fort D et al (2015) Reproducibility and repeatability of a new computerized software for sagittal spinopelvic and scoliosis curvature radiologic measurements: Keops®. Eur Spine J 24:1574–1581. https://doi.org/10.1007/s00586-015-3817-1 [DOI: 10.1007/s00586-015-3817-1]
  6. Lafage R, Ferrero E, Henry J et al (2015) Validation of a new computer-assisted tool to measure spino-pelvic parameters. Spine J 15:2493–2502. https://doi.org/10.1016/j.spinee.2015.08.067 [DOI: 10.1016/j.spinee.2015.08.067]
  7. Galbusera F, Casaroli G, Bassani T (2019) Artificial intelligence and machine learning in spine research. JOR Spine 2:e1044. https://doi.org/10.1002/jsp2.1044 [DOI: 10.1002/jsp2.1044]
  8. Cheng PM, Montagnon E, Yamashita R et al (2021) Deep learning: an update for radiologists. Radiographics 41:1427–1445. https://doi.org/10.1148/rg.2021200210 [DOI: 10.1148/rg.2021200210]
  9. Chea P, Mandell JC (2020) Current applications and future directions of deep learning in musculoskeletal radiology. Skeletal Radiol 49:183–197. https://doi.org/10.1007/s00256-019-03284-z [DOI: 10.1007/s00256-019-03284-z]
  10. Ghaednia H, Lans A, Sauder N et al (2021) Deep learning in spine surgery. Semin Spine Surg 33:100876. https://doi.org/10.1016/j.semss.2021.100876 [DOI: 10.1016/j.semss.2021.100876]
  11. Page MJ, McKenzie JE, Bossuyt PM et al (2021) The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. Syst Rev 10:89. https://doi.org/10.1186/s13643-021-01626-4 [DOI: 10.1186/s13643-021-01626-4]
  12. Galbusera F, Bassani T, Costa F et al (2018) Artificial neural networks for the recognition of vertebral landmarks in the lumbar spine. Comput Methods Biomech Biomed Eng Imaging Vis 6:447–452. https://doi.org/10.1080/21681163.2016.1261370 [DOI: 10.1080/21681163.2016.1261370]
  13. Aubert B, Vidal PA, Parent S, et al (2017) Convolutional neural network and in-painting techniques for the automatic assessment of scoliotic spine surgery from biplanar radiographs. In: 20th International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2017. Springer, Quebec City, Canada, pp 691–699. https://doi.org/10.1007/978-3-319-66185-8_78
  14. Wu H, Bailey C, Rasoulinejad P, Li S (2018) Automated comprehensive adolescent idiopathic scoliosis assessment using MVC-Net. Med Image Anal 48:1–11. https://doi.org/10.1016/j.media.2018.05.005 [DOI: 10.1016/j.media.2018.05.005]
  15. Korez R, Putzier M, Vrtovec T (2019) Automated measurement of pelvic incidence from X-ray images. In: 6th International Workshop on Computational Methods and Clinical Applications in Musculoskeletal Imaging - MSKI 2018. Springer, Granada, Spain, pp 146–152. https://doi.org/10.1007/978-3-030-11166-3_13
  16. Korez R, Putzier M, Vrtovec T (2018) Computer-assisted measurement of sagittal pelvic alignment parameters from radiographic images. Zdrav Vestn 87:519–529. https://doi.org/10.6016/ZdravVestn.2829 [DOI: 10.6016/ZdravVestn.2829]
  17. Korez R, Putzier M, Vrtovec T (2020) A deep learning tool for fully automated measurements of sagittal spinopelvic balance from X-ray images: performance evaluation. Eur Spine J 29:2295–2305. https://doi.org/10.1007/s00586-020-06406-7 [DOI: 10.1007/s00586-020-06406-7]
  18. Pang S, Leung S, Nachum IB, et al (2018) Direct automated quantitative measurement of spine via cascade amplifier regression network. In: 21st International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2018. Springer, Granada, Spain, pp 940–948. https://doi.org/10.1007/978-3-030-00934-2_104
  19. Pang S, Su Z, Leung S et al (2019) Direct automated quantitative measurement of spine by cascade amplifier regression network with manifold regularization. Med Image Anal 55:103–115. https://doi.org/10.1016/j.media.2019.04.012 [DOI: 10.1016/j.media.2019.04.012]
  20. Galbusera F, Niemeyer F, Wilke H-J et al (2019) Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach. Eur Spine J 28:951–960. https://doi.org/10.1007/s00586-019-05944-z [DOI: 10.1007/s00586-019-05944-z]
  21. Wang L, Xu Q, Leung S et al (2019) Accurate automated Cobb angles estimation using multi-view extrapolation net. Med Image Anal 58:101542. https://doi.org/10.1016/j.media.2019.101542 [DOI: 10.1016/j.media.2019.101542]
  22. Aubert B, Vazquez C, Cresson T et al (2019) Toward automated 3D spine reconstruction from biplanar radiographs using CNN for statistical spine model fitting. IEEE Trans Med Imaging 38:2796–2806. https://doi.org/10.1109/TMI.2019.2914400 [DOI: 10.1109/TMI.2019.2914400]
  23. Ernst P, Hille G, Hansen C, et al (2019) A CNN-based framework for statistical assessment of spinal shape and curvature in whole-body MRI images of large populations. In: 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2019. Springer, Shenzhen, China, pp 3–11. https://doi.org/10.1007/978-3-030-32251-9_1
  24. Cho BH, Kaji D, Cheung ZB et al (2020) Automated measurement of lumbar lordosis on radiographs using machine learning and computer vision. Global Spine J 10:611–618. https://doi.org/10.1177/2192568219868190 [DOI: 10.1177/2192568219868190]
  25. Huang J, Shen H, Wu J et al (2020) Spine Explorer: a deep learning based fully automated program for efficient and reliable quantifications of the vertebrae and discs on sagittal lumbar spine MR images. Spine J 20:590–599. https://doi.org/10.1016/j.spinee.2019.11.010 [DOI: 10.1016/j.spinee.2019.11.010]
  26. Weng C-H, Wang C-L, Huang Y-J et al (2019) Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework. J Clin Med 8:1826. https://doi.org/10.3390/jcm8111826 [DOI: 10.3390/jcm8111826]
  27. Zhang T, Zhu C, Lu Q et al (2020) A novel tool to provide predictable alignment data irrespective of source and image quality acquired on mobile phones: what engineers can offer clinicians. Eur Spine J 29:387–395. https://doi.org/10.1007/s00586-019-06264-y [DOI: 10.1007/s00586-019-06264-y]
  28. Chae D-S, Nguyen TP, Park S-J et al (2020) Decentralized convolutional neural network for evaluating spinal deformity with spinopelvic parameters. Comput Methods Programs Biomed 197:105699. https://doi.org/10.1016/j.cmpb.2020.105699 [DOI: 10.1016/j.cmpb.2020.105699]
  29. Kim DH, Jeong JG, Kim YJ et al (2021) Automated vertebral segmentation and measurement of vertebral compression ratio based on deep learning in X-ray images. J Digit Imaging 34:853–861. https://doi.org/10.1007/s10278-021-00471-0 [DOI: 10.1007/s10278-021-00471-0]
  30. Schwartz JT, Cho BH, Tang P et al (2021) Deep learning automates measurement of spinopelvic parameters on lateral lumbar radiographs. Spine 46:E671–E678. https://doi.org/10.1097/BRS.0000000000003830 [DOI: 10.1097/BRS.0000000000003830]
  31. Yang G, Fu X, Xu N, et al (2020) A landmark estimation and correction network for automated measurement of sagittal spinal parameters. In: 27th International Conference on Neural Information Processing - ICONIP 2020. Springer, Bangkok, Thailand, pp 213–221. https://doi.org/10.1007/978-3-030-63820-7_24
  32. Cina A, Bassani T, Panico M et al (2021) 2-step deep learning model for landmarks localization in spine radiographs. Sci Rep 11:9482. https://doi.org/10.1038/s41598-021-89102-w [DOI: 10.1038/s41598-021-89102-w]
  33. Nguyen TP, Chae D-S, Park S-J et al (2021) Deep learning system for Meyerding classification and segmental motion measurement in diagnosis of lumbar spondylolisthesis. Biomed Signal Process Control 65:102371. https://doi.org/10.1016/j.bspc.2020.102371 [DOI: 10.1016/j.bspc.2020.102371]
  34. Shin Y, Han K, Lee YH (2020) Temporal trends in cervical spine curvature of South Korean adults assessed by deep learning system segmentation, 2006–2018. JAMA Netw Open 3:e2020961. https://doi.org/10.1001/jamanetworkopen.2020.20961 [DOI: 10.1001/jamanetworkopen.2020.20961]
  35. Grover P, Siebenwirth J, Caspari C et al (2020) [Abstracts of the 15th German Spine Congress] Can artificial intelligence support or even replace physicians in measuring the sagittal balance? – a validation study on preoperative and postoperative images of 170 patients. Eur Spine J 29:2865–2866. https://doi.org/10.1007/s00586-020-06630-1 [DOI: 10.1007/s00586-020-06630-1]
  36. Tran VL, Lin H-Y, Liu H-W (2021) MBNet: a multi-task deep neural network for semantic segmentation and lumbar vertebra inspection on X-ray images. In: 15th Asian Conference on Computer Vision - ACCV 2020. Springer, Kyoto, Japan, pp 635–651. https://doi.org/10.1007/978-3-030-69541-5_38
  37. Yeh Y-C, Weng C-H, Huang Y-J et al (2021) Deep learning approach for automatic landmark detection and alignment analysis in whole-spine lateral radiographs. Sci Rep 11:7618. https://doi.org/10.1038/s41598-021-87141-x [DOI: 10.1038/s41598-021-87141-x]
  38. Franke J, Grover P, Siebenwirth J et al (2021) [Abstracts of EUROSPINE 2021] Can artificial intelligence support or even replace physicians in measuring the sagittal balance? A validation study on preoperative and postoperative images of 170 patients. Brain Spine 1:100062. https://doi.org/10.1016/j.bas.2021.100062 [DOI: 10.1016/j.bas.2021.100062]
  39. Masood RF, Taj IA, Khan MB et al (2022) Deep learning based vertebral body segmentation with extraction of spinal measurements and disorder disease classification. Biomed Signal Process Control 71:103230. https://doi.org/10.1016/j.bspc.2021.103230 [DOI: 10.1016/j.bspc.2021.103230]
  40. Orosz L, Haines CM, Thomson A et al (2021) [Proceedings of the 36th Annual Meeting of the North American Spine Society] 74. Novel artificial intelligence algorithm can accurately and independently measure spinopelvic parameters. Spine J 21:S36–S37. https://doi.org/10.1016/j.spinee.2021.05.099 [DOI: 10.1016/j.spinee.2021.05.099]
  41. Nguyen TP, Jung JW, Yoo YJ et al (2022) Intelligent evaluation of global spinal alignment by a decentralized convolutional neural network. J Digit Imaging. https://doi.org/10.1007/s10278-021-00533-3 [DOI: 10.1007/s10278-021-00533-3]
  42. Zhang K, Xu N, Guo C, Wu J (2022) MPF-Net: an effective framework for automated Cobb angle estimation. Med Image Anal 75:102277. https://doi.org/10.1016/j.media.2021.102277 [DOI: 10.1016/j.media.2021.102277]
  43. Iriondo C, Mehany S, Shah R et al (2022) Institution-wide shape analysis of 3D spinal curvature and global alignment parameters. J Orthop Res. https://doi.org/10.1002/jor.25213 [DOI: 10.1002/jor.25213]
  44. Zhou S, Yao H, Ma C et al (2022) Artificial intelligence X-ray measurement technology of anatomical parameters related to lumbosacral stability. Eur J Radiol 146:110071. https://doi.org/10.1016/j.ejrad.2021.110071 [DOI: 10.1016/j.ejrad.2021.110071]
  45. Löchel J, Putzier M, Dreischarf M et al (2021) [Abstracts of the 16th German Spine Congress] Evaluation of artificial intelligence based image analysis of sagittal profile. Eur Spine J 30:3350. https://doi.org/10.1016/j.bas.2021.100062 [DOI: 10.1016/j.bas.2021.100062]
  46. Azimi P, Yazdanian T, Benzel EC et al (2021) Sagittal balance of the cervical spine: a systematic review and meta-analysis. Eur Spine J 30:1411–1439. https://doi.org/10.1007/s00586-021-06825-0 [DOI: 10.1007/s00586-021-06825-0]
  47. Schlösser TPC, Castelein RM, Grobost P et al (2021) Specific sagittal alignment patterns are already present in mild adolescent idiopathic scoliosis. Eur Spine J 30:1881–1887. https://doi.org/10.1007/s00586-021-06772-w [DOI: 10.1007/s00586-021-06772-w]
  48. Joshi RS, Lau D, Scheer JK et al (2021) State-of-the-art reviews predictive modeling in adult spinal deformity: applications of advanced analytics. Spine Deform 9:1223–1239. https://doi.org/10.1007/s43390-021-00360-0 [DOI: 10.1007/s43390-021-00360-0]
  49. Cheung JPY, Kuang X, Lai MKL et al (2022) Learning-based fully automated prediction of lumbar disc degeneration progression with specified clinical parameters and preliminary validation. Eur Spine J. https://doi.org/10.1007/s00586-021-07020-x [DOI: 10.1007/s00586-021-07020-x]
  50. Wirries A, Geiger F, Hammad A et al (2021) Artificial intelligence facilitates decision-making in the treatment of lumbar disc herniations. Eur Spine J 30:2176–2184. https://doi.org/10.1007/s00586-020-06613-2 [DOI: 10.1007/s00586-020-06613-2]
  51. Baur D, Bieck R, Berger J et al (2022) Analysis of the paraspinal muscle morphology of the lumbar spine using a convolutional neural network (CNN). Eur Spine J. https://doi.org/10.1007/s00586-021-07073-y [DOI: 10.1007/s00586-021-07073-y]
  52. Bernstein P, Metzler J, Weinzierl M et al (2021) Radiographic scoliosis angle estimation: spline-based measurement reveals superior reliability compared to traditional Cobb method. Eur Spine J 30:676–685. https://doi.org/10.1007/s00586-020-06577-3 [DOI: 10.1007/s00586-020-06577-3]
  53. Sun Y, Xing Y, Zhao Z et al (2022) Comparison of manual versus automated measurement of Cobb angle in idiopathic scoliosis based on a deep learning keypoint detection technology. Eur Spine J. https://doi.org/10.1007/s00586-021-07025-6 [DOI: 10.1007/s00586-021-07025-6]
  54. Protopsaltis TS, Lafage R, Smith JS et al (2018) The lumbar pelvic angle, the lumbar component of the T1 pelvic angle, correlates with HRQOL, PI-LL mismatch, and it predicts global alignment. Spine 43:681–687. https://doi.org/10.1097/BRS.0000000000002346 [DOI: 10.1097/BRS.0000000000002346]
  55. Schwab F, Ungar B, Blondel B et al (2012) Scoliosis Research Society-Schwab adult spinal deformity classification: a validation study. Spine 37:1077–1082. https://doi.org/10.1097/BRS.0b013e31823e15e2 [DOI: 10.1097/BRS.0b013e31823e15e2]
  56. Pan C, Wang G, Li Y et al (2021) Predictive model of global tilt (GT) determined by individual thoracic kyphosis, lumbar lordosis and pelvic incidence in the human degenerative spine. Eur Spine J 30:3191–3199. https://doi.org/10.1007/s00586-021-06947-5 [DOI: 10.1007/s00586-021-06947-5]
  57. Yilgor C, Sogunmez N, Yavuz Y et al (2017) Relative lumbar lordosis and lordosis distribution index: individualized pelvic incidence-based proportional parameters that quantify lumbar lordosis more precisely than the concept of pelvic incidence minus lumbar lordosis. Neurosurg Focus 43:E5. https://doi.org/10.3171/2017.8.FOCUS17498 [DOI: 10.3171/2017.8.FOCUS17498]
  58. Barrey C, Roussouly P, Le Huec J-C et al (2013) Compensatory mechanisms contributing to keep the sagittal balance of the spine. Eur Spine J 22:S834–S841. https://doi.org/10.1007/s00586-013-3030-z [DOI: 10.1007/s00586-013-3030-z]
  59. Ferrero E, Guigui P, Khalifé M et al (2021) Global alignment taking into account the cervical spine with odontoid hip axis angle (OD-HA). Eur Spine J 30:3647–3655. https://doi.org/10.1007/s00586-021-06991-1 [DOI: 10.1007/s00586-021-06991-1]
  60. Protopsaltis T, Schwab F, Bronsard N et al (2014) The T1 pelvic angle, a novel radiographic measure of global sagittal deformity, accounts for both spinal inclination and pelvic tilt and correlates with health-related quality of life. J Bone Joint Surg Am 96:1631–1640. https://doi.org/10.2106/JBJS.M.01459 [DOI: 10.2106/JBJS.M.01459]
  61. Lee SH, Hyun SJ, Jain A (2020) Cervical sagittal alignment literature review and future directions. Neurospine 17:478–496. https://doi.org/10.14245/ns.2040392.196 [DOI: 10.14245/ns.2040392.196]
  62. Knott PT, Mardjetko SM, Techy F (2010) The use of the T1 sagittal angle in predicting overall sagittal balance of the spine. Spine J 10:994–998. https://doi.org/10.1016/j.spinee.2010.08.031 [DOI: 10.1016/j.spinee.2010.08.031]
  63. Alanay A, Pekmezci M, Karaeminogulları O et al (2007) Radiographic measurement of the sagittal plane deformity in patients with osteoporotic spinal fractures evaluation of intrinsic error. Eur Spine J 16:2126–2132. https://doi.org/10.1007/s00586-007-0474-z [DOI: 10.1007/s00586-007-0474-z]
  64. Willemink MJ, Koszek WA, Hardell C et al (2020) Preparing medical imaging data for machine learning. Radiology 295:4–15. https://doi.org/10.1148/radiol.2020192224 [DOI: 10.1148/radiol.2020192224]
  65. Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6:60. https://doi.org/10.1186/s40537-019-0197-0 [DOI: 10.1186/s40537-019-0197-0]
  66. Ronneberger O, Fischer P, Brox S (2015) U-Net: convolutional networks for biomedical image segmentation. In: 18th International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015. Springer, Munich, Germany, pp 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
  67. Zhang L, Shi L, Cheng JC-Y et al (2021) LPAQR-Net: efficient vertebra segmentation from biplanar whole-spine radiographs. IEEE J Biomed Health Inform 25:2710–2721. https://doi.org/10.1109/JBHI.2021.3057647 [DOI: 10.1109/JBHI.2021.3057647]
  68. Tran VL, Lin H-Y, Liu H-W, et al (2021) BiLuNet: a multi-path network for semantic segmentation on X-ray images. In: 25th International Conference on Pattern Recognition - ICPR 2020. IEEE, Milan, Italy, pp 10034–10041. https://doi.org/10.1109/ICPR48806.2021.9412027
  69. Zhou J, Damasceno PF, Chachad R et al (2020) Automatic vertebral body segmentation based on deep learning of Dixon images for bone marrow fat fraction quantification. Front Endocrinol 11:612. https://doi.org/10.3389/fendo.2020.00612 [DOI: 10.3389/fendo.2020.00612]
  70. Liang S, Liu H, Chen C et al (2021) Research on multi-path dense networks for MRI spinal segmentation. PLoS ONE 16:e0248303. https://doi.org/10.1371/journal.pone.0248303 [DOI: 10.1371/journal.pone.0248303]
  71. Cheng P, Yang Y, Yu H, He Y (2021) Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net. Sci Rep 11:22156. https://doi.org/10.1038/s41598-021-01296-1 [DOI: 10.1038/s41598-021-01296-1]
  72. Liu P, Han H, Du Y et al (2021) Deep learning to segment pelvic bones: large-scale CT datasets and baseline models. Int J Comput Assist Radiol Surg 16:749–756. https://doi.org/10.1007/s11548-021-02363-8 [DOI: 10.1007/s11548-021-02363-8]

MeSH Term

Cross-Sectional Studies
Deep Learning
Humans
Lumbar Vertebrae
Lumbosacral Region
Pelvis
Radiography
Journal Article Systematic Review Research Support, Non-U.S. Gov't
Article has an altmetric score of 1

Word Cloud

Created with Highcharts 10.0.0DLmeasurementspinopelvicsagittalspinemeasurementsbalancestudiesreviewparametersappliedSpinopelvicmethodsdeeplearningrecordsresultingimagedatasetsperformancelumbarwholeX-raysparametererrorreferenceanalyticsPURPOSE:summarizecriticallyevaluateexistingbasedMETHODS:ThreedatabasesPubMedWoSScopusqueriedusingkeywordsrelatedscreening529augmentedspecificwebsearch34published20172022includedfinalevaluatedperspectiveobservedpropertiesmethodologyRESULTS:Studiesreported18differentactualnumberdependedfieldviewImagecomposedlateralbiplanarmagneticresonancecrosssectionsincreasingsizeenrichedaugmentationtechniquesapproachedeitherlandmarkdetectionstructuresegmentationU-Netfrequentlyarchitecturelatestachievedexcellenttermsmeanabsolutemanual~ 2°or ~ 1 mmCONCLUSION:Althoughapplicationrelativelycomplexarchitecturesresultedimprovedaccuracyfuturefocusmulti-institutionmulti-observeranalyseswelluncertaintyestimationhandlingimplementationsintegrationclinicalworkflowadvanceswillenhancepredictiveLEVELOFEVIDENCEI:Diagnostic:individualcross-sectionalconsistentlystandardblindinglearning:systematiccriticalevaluationArtificialintelligenceDeepPredictiveSagittalSystematic

Similar Articles

Cited By